OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

v3dv: trivially implement VK_KHR_separate_depth_stencil_layouts

Browse Source 
We don't currently benefit from seeing barriers and layout
transitions that affect just the depth or stencil aspects,
so we don't expose this feature.

Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16344>
This commit is contained in:
Iago Toral Quiroga
2022-05-05 09:54:38 +02:00
committed by Marge Bot
parent 32223ac67f
commit 1442d77bc5
2 changed files with 17 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/features.txt
View File

@@ -454,7 +454,7 @@ Vulkan 1.2 -- all DONE: anv, vn
VK_KHR_image_format_list DONE (anv, lvp, radv, tu, v3dv, vn)
VK_KHR_imageless_framebuffer DONE (anv, lvp, radv, tu, v3dv, vn)
VK_KHR_sampler_mirror_clamp_to_edge DONE (anv, lvp, radv, tu, v3dv, vn)
VK_KHR_separate_depth_stencil_layouts DONE (anv, lvp, radv, vn, tu)
VK_KHR_separate_depth_stencil_layouts DONE (anv, lvp, radv, vn, v3dv, tu)
VK_KHR_shader_atomic_int64 DONE (anv/gen9+, lvp, radv, vn)
VK_KHR_shader_float16_int8 DONE (anv/gen8+, lvp, radv, tu, vn)
VK_KHR_shader_float_controls DONE (anv/gen8+, lvp, radv, tu, vn)

16
src/broadcom/vulkan/v3dv_device.c
View File

@@ -137,6 +137,7 @@ get_device_extensions(const struct v3dv_physical_device *device,
.KHR_maintenance2 = true,
.KHR_maintenance3 = true,
.KHR_multiview = true,
.KHR_separate_depth_stencil_layouts = true,
.KHR_shader_non_semantic_info = true,
.KHR_sampler_mirror_clamp_to_edge = true,
.KHR_storage_buffer_storage_class = true,
@@ -1169,6 +1170,21 @@ v3dv_GetPhysicalDeviceFeatures2(VkPhysicalDevice physicalDevice,
* not lead to best performance so let's just not support it.
*/
.scalarBlockLayout = false,
/* This tells applications 2 things:
*
* 1. If they can select just one aspect for barriers. For us barriers
* decide if we need to split a job and we don't care if it is only
* for one of the aspects of the image or both, so we don't really
* benefit from seeing barriers that select just one aspect.
*
* 2. If they can program different layouts for each aspect. We
* generally don't care about layouts, so again, we don't get any
* benefits from this to limit the scope of image layout transitions.
*
* Since we cannot offer any advantages to applications that use separate
* layouts for D/S, don't expose the feature.
*/
.separateDepthStencilLayouts = false,
.storageBuffer8BitAccess = true,
.storagePushConstant8 = true,
.imagelessFramebuffer = true,